-
Don't Vibe Your Infrastructure
-
The Craftsman's Goodbye
-
Identity Isn't Intent
-
Be Vague on Purpose
-
The Headcount Math Is Wrong
-
You Can't Edit What You Can't Write
-
The Machine Has Better Discipline Than Your Team
-
Salesforce Put Its CRM Inside Claude
-
Microsoft's Claude Looks Cheaper Until You Read the Prerequisite
-
Claude Buddy Stopped Being an Extension and Became an Ecosystem
-
Core-Agnostic Still Needs a Core
-
Banks Don't Need Another Agent. They Need a Context Layer.
-
Fiserv Forum 2026
Three dispatches from Fiserv Forum 2026: an architecture-first read on agentOS, the reliability that agents inherit from the core beneath them, and the data problem that decides whether any of it grounds. Written for the architect asking what actually ships versus what opens a statement of work.
-
UiPath Isn't the New MuleSoft. It's the New Power Platform.
-
Steal the Contract, Not the Catalog: Karpathy's LLM Wiki, Two Ways, for Regulated Banks
-
The AI Employee Roster Was Built for a Plumber. Every Line Has a Bank-Sized Twin.
-
Business Is the Programming Language
-
The AI Factory Has Five Rungs. Most Banks Are on the Second.
-
The Harness Went Multiplayer. Build What It Skips.
-
Java's AI Moment Is Here. The Gap Was Never Technical.
-
The Killer Feature Is the Signature
-
The Model Stopped Being the Product
-
Only Thirty-Two Percent of the Time Can the Agent Prove It's Itself
-
The Paperclip Maximizer Clocked In
-
The Customer Authorized a Human, Not a Fleet
-
When the Agent Reaches for the Card
-
The Second Brain Doesn't Ship
-
The Bank Got Dumber While Its People Got Smarter
-
You're Renting the Model. Own the Harness.
-
Documentation Is the Code Now
-
The Model Was Never the Problem
-
Streaming in Name Only
-
The Field Guide I Wrote for My Family Beats Most Enterprise AI Strategies
-
The Load-Bearing Agreement
-
The Gate Was Built for a Human
-
We Inspect the Traffic, So We're Covered
-
An ERD Is the Floor, Not the Ceiling
-
Foundry and Fabric, Not Foundry or Fabric
-
The Architecture Is Clear. The Investment Isn't.
-
Markdown Is the Knowledge Layer
-
The API Catalog Is the Tool Catalog
-
Fifteen Pages, Nothing to Ship
-
Your Size Was Always the Advantage
-
Architecture Is the Prompt
-
Agents Don't Commute
-
WSL Is Not Optional
-
Microsoft Conceded the Harness. Then It Moved the Moat.
-
Governance or Containment: The Real Question I'm Bringing to Build
-
Six Primitives for a Code Factory
-
Who Scans Whom: The Agent Discovery Asymmetry Between MuleSoft and Microsoft
-
I Built Clerko: A Hermes-Powered Legal Agent for My Attorney Son
-
My First Microsoft Build: What I'm Actually Watching
-
What witness.ai Doesn't See
-
Beyond the Rebrand: What Anypoint Omni Gateway Actually Changes
-
The Bottleneck Was Never the Code
-
When Your Team Starts Building
-
From Paperclip to Production: The Open-Source SDLC/SRE Bet Every Enterprise Is Weighing
-
Claude Is Already in the Building
-
The Aircraft Carrier's Business Brain
-
The Zero-Copy Promise
-
Same Question, Different Worlds: What Your Team's AI Readiness Actually Looks Like
-
I Use Microsoft Every Day. I Don't Trust Them.
-
Platform Strategy & Vendor Economics
Where lock-in goes when formats open up, protocols standardize, and AI agents enter the stack. An ongoing analysis of enterprise platform decisions, vendor positioning, and the switching costs that compound when nobody is looking.
-
Claude Code: Where It Actually Runs
-
TDX 2026
Dispatches from Salesforce TDX 2026: architecture analysis, vendor reality checks, and what the pitch actually means for an Azure-invested enterprise.
-
Agent as a Service Is Real. The Vendor Pitch Isn't.
-
Claude Buddy Stopped Being a Tool and Became an Extension
-
The Stack Nobody Designed
-
Context Engineering Is Infrastructure, Not a Skill
-
Same Person, Five Systems: The Data Identity Problem Banks Still Can't Solve
-
The Documentation Dividend: What AI Replacing Knowledge Workers Actually Looks Like Inside a Bank
-
Everything Is Skill Issue
-
The Sandbox Isn't the Hard Part
-
Automating Chaos Produces Automated Chaos
-
AI Can Write Your Terraform. Can Your Organization Deploy It?
-
Python Won't Run Your Bank: The Language Stack Reckoning for Enterprise AI
-
Life as Infrastructure
The Four Burners theory says you must sacrifice parts of your life to succeed. But what if the real problem isn't competing demands, but bad architecture? A three-part series applying systems thinking to life balance.
-
The Architect's Dilemma: When Your AI Vendor Powers Both Sides
-
Dozens of Portals, One Identity: How an Architect Thinks About Enterprise Identity Consolidation
-
Architecture Without Architects: A Pragmatic Playbook for Regulated Banks
-
Prompting Split Into Four Skills. Infrastructure Is the Fifth.
-
The Reconciliation Loop: Desired State Is Not New. The Executor Is.
-
The Personal AI Wars: A Developer's Guide
-
The Browser Is Not an API
-
My Three Gurus
Three men, separated by a century and a half, teaching the same lessons through radically different languages. A Victorian monk, a clinical psychologist, and a modern entrepreneur converge on truth.
-
When It Hits Home
A 3-part series: one father, three children, three careers facing the same AI shift from different angles.
-
Judgment Is the New Moat
-
The 48-Hour Repricing: What a Legal Plugin Taught Banking About Its Software Future
-
When Everything Is Privileged, Nothing Is
-
The Regulated AI Stack
A 10-part series exploring the challenges, architectures, and frameworks for adopting AI in regulated industries.
-
2025: The Year of Loss and Clarity
-
Claude Code vs Copilot CLI: Making the Enterprise Case
-
The Clone Problem: Why Your AI Personal Agent Can't Follow You to Work
-
From Threads to Trust: A Framework for Measuring Your Agentic Engineering Growth
-
What PAI's 7-Phase Loop Taught Me About Claude Buddy's Missing Piece
-
Why I Built Claude Buddy: Bringing AI-Driven Development to Regulated Banking